arm_mult_q15.c

00001 /* ----------------------------------------------------------------------  
00002 * Copyright (C) 2010 ARM Limited. All rights reserved.  
00003 *  
00004 * $Date:        29. November 2010  
00005 * $Revision:    V1.0.3  
00006 *  
00007 * Project:      CMSIS DSP Library  
00008 * Title:        arm_mult_q15.c  
00009 *  
00010 * Description:  Q15 vector multiplication.  
00011 *  
00012 * Target Processor: Cortex-M4/Cortex-M3
00013 *  
00014 * Version 1.0.3 2010/11/29 
00015 *    Re-organized the CMSIS folders and updated documentation.  
00016 *   
00017 * Version 1.0.2 2010/11/11  
00018 *    Documentation updated.   
00019 *  
00020 * Version 1.0.1 2010/10/05   
00021 *    Production release and review comments incorporated.  
00022 *  
00023 * Version 1.0.0 2010/09/20   
00024 *    Production release and review comments incorporated.  
00025 *  
00026 * Version 0.0.5  2010/04/26   
00027 *    incorporated review comments and updated with latest CMSIS layer  
00028 *  
00029 * Version 0.0.3  2010/03/10   
00030 *    Initial version  
00031 * -------------------------------------------------------------------- */ 
00032  
00033 #include "arm_math.h" 
00034  
00035 /**  
00036  * @ingroup groupMath  
00037  */ 
00038  
00039 /**  
00040  * @addtogroup BasicMult  
00041  * @{  
00042  */ 
00043  
00044  
00045 /**  
00046  * @brief           Q15 vector multiplication  
00047  * @param[in]       *pSrcA points to the first input vector  
00048  * @param[in]       *pSrcB points to the second input vector  
00049  * @param[out]      *pDst points to the output vector  
00050  * @param[in]       blockSize number of samples in each vector  
00051  * @return none.  
00052  *  
00053  * <b>Scaling and Overflow Behavior:</b>  
00054  * \par  
00055  * The function uses saturating arithmetic.  
00056  * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.  
00057  */ 
00058  
00059 void arm_mult_q15( 
00060   q15_t * pSrcA, 
00061   q15_t * pSrcB, 
00062   q15_t * pDst, 
00063   uint32_t blockSize) 
00064 { 
00065   uint32_t blkCnt;                               /* loop counters */ 
00066  
00067   /* loop Unrolling */ 
00068   blkCnt = blockSize >> 2u; 
00069  
00070   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.  
00071    ** a second loop below computes the remaining 1 to 3 samples. */ 
00072   while(blkCnt > 0u) 
00073   { 
00074     /* C = A * B */ 
00075     /* Multiply the inputs and store the result in the destination buffer */ 
00076     *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16); 
00077     *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16); 
00078     *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16); 
00079     *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16); 
00080  
00081     /* Decrement the blockSize loop counter */ 
00082     blkCnt--; 
00083   } 
00084  
00085   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.  
00086    ** No loop unrolling is used. */ 
00087   blkCnt = blockSize % 0x4u; 
00088  
00089   while(blkCnt > 0u) 
00090   { 
00091     /* C = A * B */ 
00092     /* Multiply the inputs and store the result in the destination buffer */ 
00093     *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16); 
00094  
00095     /* Decrement the blockSize loop counter */ 
00096     blkCnt--; 
00097   } 
00098 } 
00099  
00100 /**  
00101  * @} end of BasicMult group  
00102  */